Energy storage management method, device and equipment for modular tongue flap gate and storage medium

Abstract

The invention discloses an energy storage management method, device and equipment of a modular tongue flap gate and a storage medium, and relates to the technical field of energy storage, and the method utilizes the characteristic that the water temperature is gradually reduced along with the increase of the water depth, starts with the heat dissipation of an energy storage part, and serves as the heat dissipation index of the energy storage part at different water depths, thereby improving the energy storage efficiency. Because the energy storage part (such as a battery pack) can release heat during charging and discharging, the energy storage part at a colder water temperature has a larger temperature difference, so that heat dissipation of the energy storage part is more facilitated, more charging amount is allocated to the energy storage part at the colder water temperature, the more charging amount means more electricity consumption, and the energy storage part is more energy-saving and environment-friendly. The whole heat release process can be carried out in a colder water temperature environment, so that good heat dissipation of the energy storage part in the whole process is ensured, and machine learning is introduced to predict future water temperature, so that the system can predict future water temperature change and make charging preparation in advance, and the hysteresis of charging behaviors is eliminated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage, in particular to an energy storage management method, device and equipment of a modular flap gate and a storage medium. BACKGROUND

[0002] Layered water extraction is a technology for extracting water layers at different depths from a reservoir, lake or water body. The main purpose is to selectively obtain water bodies at specific depths according to water quality, temperature or ecological needs. Since the water body usually has vertical stratification phenomena (such as temperature stratification, dissolved oxygen stratification, and nutrient salt distribution difference), layered water extraction extracts water sources from the target water layer through an adjustable water intake (such as a multi-layer gate or a floating cylinder water extractor), avoiding the extraction of unsuitable water layers.

[0003] Due to the characteristics of high cost, complex technology and strong specificity of layered water extraction technology, layered water extraction has not been widely popularized. At present, layered water extraction technology can only be seen in large water conservancy projects and a small number of drinking water reservoirs.

[0004] Due to the technical complexity of layered water extraction technology, modular flap gates have appeared on the market through modular installation. Such modular modular flap gates have the functions of unlimited charging and energy storage. Specifically, the induction coil in the modular flap gate wirelessly induces the power supply coil in the gate slot to achieve the effect of charging, and stores the charged electric energy in the energy storage component. It not only does not affect daily use, but also is convenient to disassemble and assemble, avoiding the technical difficulties of wiring and one-piece forming.

[0005] However, such modular modular flap gates also bring technical challenges in underwater energy storage. For example, the charging and discharging of underwater energy storage equipment is difficult to inspect and monitor, and the modular flap gate is a new device. The monitoring and management of each component of the modular flap gate are still in the blank and experimental stage. Overcharging and overdischarging of underwater energy storage equipment during daily use are not easy to be discovered in time, and overcharging and overdischarging not only have high frequency, but also easily damage the energy storage equipment, resulting in damage to the physical structure and chemical stability of the energy storage equipment. Lightly, it affects performance and service life, and heavily, it leads to leakage pollution of water body or explosion. The foregoing problems further increase the difficulty of energy storage management due to the characteristics of difficult inspection of underwater environment. SUMMARY

[0006] The main purpose of the present application is to provide an energy storage management method, device and equipment of a modular flap gate and a storage medium to solve the problem of difficult operation and management of underwater energy storage based on a modular flap gate in the prior art.

[0007] In order to achieve the above purpose, the present application provides the following technical solutions: An energy storage management method of a modular flap door, the modular flap door is applied to a layered water taking working door, the layered water taking working door comprises at least one group of modular flap doors with different height differences, all the modular flap doors are clamped in a door groove of a dam body and are used for rotating respectively according to different water taking requirements to achieve the purpose of being opened or closed respectively, each modular flap door is respectively provided with a wireless power supply part and an energy storage part electrically connected with the wireless power supply part, and the energy storage management method comprises the following steps: Step S1, respectively acquiring the water surface based underwater depth of each modular flap door, and respectively acquiring the water temperature of each underwater depth based on a preset detection interval; Step S2, training and learning the water temperature of all underwater depths by a machine learning machine to obtain a water temperature prediction model; Step S3, defining a preset prediction interval same as a step of the preset detection interval, and predicting a plurality of future water temperatures based on a plurality of preset prediction intervals by the water temperature prediction model; Step S4, acquiring a minimum temperature and a maximum temperature in all water temperatures and all future water temperatures; Step S5, taking the minimum temperature and the maximum temperature as an interval minimum value and an interval maximum value of a temperature interval respectively, and constructing the temperature interval; Step S6, equally dividing the temperature interval into at least two continuous subintervals; Step S7, assigning an appropriate electric quantity to each subinterval, and all appropriate electric quantities decrease with the increase of each subinterval; Step S8, respectively acquiring the future water temperature of the underwater depth where each modular flap door is located, and judging whether the residual electric quantity of the current modular flap door is less than the corresponding appropriate electric quantity when the future water temperature of the current modular flap door arrives, if yes, executing step S9; Step S9, charging the energy storage part of the current modular flap door until stopping charging when the corresponding appropriate electric quantity is reached.

[0008] As a further improvement of the present application, step S9, charging the energy storage part of the current modular flap door until stopping charging when the corresponding appropriate electric quantity is reached, and then comprising: Step S10, acquiring the device temperature when the current energy storage part is not charged and the device temperature when the current energy storage part is charged based on the preset detection interval; Step S20, converting all the device temperatures when the current energy storage part is not charged into a non-charging temperature curve based on a time process; Step S30, deriving the non-charging temperature curve to obtain a non-charging temperature slope; Step S40, converting all the device temperatures when the current energy storage part is charged into a charging temperature curve based on a time process; Step S50, derive the charging temperature curve to obtain a charging temperature slope; Step S60, if at least one of the uncharged temperature slope or the charging temperature slope exceeds the preset slope threshold, execute step S70; Step S70, determine that the current energy storage device is abnormal.

[0009] As a further improvement of the present application, step S70, determine that the current energy storage device is abnormal, then includes: Step S100, mark the energy storage device whose uncharged temperature slope exceeds the preset slope threshold as a discharge abnormal energy storage device; Step S200, mark all the modularized flap doors corresponding to the discharge abnormal energy storage devices as discharge abnormal modularized flap doors; Step S300, obtain the position information and equipment number of each abnormal modularized flap door respectively, and pack them into a discharge abnormal data packet; Step S400, send all the discharge abnormal data packets to an external monitoring end; Step S500, mark the energy storage device whose charging temperature slope exceeds the preset slope threshold as a charging abnormal energy storage device; Step S600, repeat steps S200 to S300 with all the charging abnormal energy storage devices as the execution subject to obtain a charging abnormal data packet; Step S700, send all the charging abnormal data packets to the external monitoring end.

[0010] As a further improvement of the present application, step S1, obtain the water depth of each modularized flap door based on the water surface, and obtain the water temperature of each water depth based on a preset detection interval, then includes: Step S1000, perform one-dimensional linear fitting on all the water temperatures of each preset detection interval respectively to obtain a water temperature function; Step S2000, determine whether each water temperature function is monotonically decreasing respectively, and mark the water temperature function that is not monotonically decreasing as an abnormal function; Step S3000, determine whether the front and rear several water temperature functions of the current abnormal function are all abnormal functions based on the time sequence, if yes, execute step S4000; Step S4000, obtain the inflection point of each abnormal function and the water depth corresponding to each inflection point respectively; Step S5000, mark the external temperature measuring device corresponding to the water depth with the highest occurrence frequency as a faulty temperature measuring device; Step S6000, pack all the fault temperature measuring pieces and the corresponding underwater depths into a fault data packet; Step S7000, send the fault data packet to an external monitoring end.

[0011] As a further improvement of the present application, step S9, charge the energy storage piece of the current modularized flap door until the corresponding required electric quantity is reached, and then stop charging, and the following includes: Step S10000, record the charging start time stamp, charging duration, and energy storage piece device number receiving charging based on each charging behavior, and pack them into a charging record packet; Step S20000, send the charging record packet to an external monitoring end.

[0012] As a further improvement of the present application, step S2, train and learn the water temperature of all underwater depths through a machine learning machine to obtain a water temperature prediction model, including: Step S21, integrate all water temperatures of the current underwater depth into a data set; Step S22, divide the current data set into a training set, a validation set, and a test set according to a preset ratio; Step S23, define a neural network model with at least one hidden layer; Step S24, train the current training set through the neural network model, and update the weights and biases of the neural network model through the back propagation algorithm according to the loss function of the training result and the current validation set; Step S25, repeat step S24 for several times until the loss function reaches a minimum value; Step S26, obtain the neural network model corresponding to the minimum value of the loss function and define it as the water temperature prediction model.

[0013] As a further improvement of the present application, step S3, define a preset prediction interval same as the preset detection interval step, and predict several future water temperatures based on several preset prediction intervals through the water temperature prediction model, including: Step S31, input the current test set into the water temperature prediction model corresponding to the current underwater depth; Step S32, obtain the future water temperature of the next preset prediction interval through the forward propagation of the current water temperature prediction model; Step S33, input the future water temperature of the next preset prediction interval into the current water temperature prediction model as an iteration subject, and repeat step S32 to obtain several future water temperatures.

[0014] In order to achieve the above purpose, the present application also provides the following technical solutions: An energy storage management device of a modular flap door, the energy storage management device is applied to the energy storage management method as described above, and the energy storage management device comprises: An underwater depth and temperature acquisition module is configured to acquire the water surface-based underwater depth of each modular flap door, and acquire the water temperature of each underwater depth based on a preset detection interval. A water temperature prediction model acquisition module is configured to train and learn the water temperature of all underwater depths by a machine learning machine to obtain a water temperature prediction model. A future water temperature prediction module is configured to define a preset prediction interval identical to the preset detection interval step, and predict a plurality of future water temperatures based on the plurality of preset prediction intervals by the water temperature prediction model. A future water temperature extreme value acquisition module is configured to acquire the temperature minimum value and the temperature maximum value in all water temperatures and all future water temperatures. A temperature interval construction module is configured to construct a temperature interval by taking the temperature minimum value and the temperature maximum value as the interval minimum value and the interval maximum value of the temperature interval, respectively. A temperature interval division module is configured to divide the temperature interval into at least two continuous subintervals. A required power assignment module is configured to assign a required power to each subinterval, and all required powers decrease with the increase of each subinterval. A modular flap door residual power judgment module is configured to acquire the future water temperature of the underwater depth where each modular flap door is located, and judge whether the residual power of the current modular flap door is less than the corresponding required power when the future water temperature of the current modular flap door arrives. A modular flap door energy storage component charging module is configured to charge the energy storage component of the current modular flap door if the residual power of the current modular flap door is less than the corresponding required power, and stop charging when the corresponding required power is reached.

[0015] To achieve the above purpose, the present application also provides the following technical solutions: An electronic device comprises a processor and a memory coupled to the processor, the memory stores program instructions executable by the processor; the processor executes the program instructions stored in the memory to implement the energy storage management method of the modular flap door as described above.

[0016] To achieve the above purpose, the present application also provides the following technical solutions: A storage medium, the storage medium stores program instructions, the program instructions are executed by the processor to implement the energy storage management method of the modular flap door as described above.

[0017] The application obtains the water surface based underwater depth of each modular flap door respectively, and obtains the water temperature of each underwater depth based on a preset detection interval respectively; the water temperature of all underwater depths is trained and learned by a machine learning machine to obtain a water temperature prediction model; a preset prediction interval same as the preset detection interval step is defined, and a plurality of future water temperatures are predicted based on a plurality of preset prediction intervals by the water temperature prediction model; a minimum temperature and a maximum temperature in all water temperatures and all future water temperatures are obtained; the minimum temperature and the maximum temperature are taken as an interval minimum value and an interval maximum value of a temperature interval respectively, and the temperature interval is constructed; the temperature interval is equally divided into at least two continuous subintervals; an expected power is given to each subinterval, and all expected powers decrease with the increase of each subinterval; the future water temperature of the underwater depth where each modular flap door is located is obtained respectively, and when the future water temperature of the current modular flap door arrives, it is judged whether the residual power of the current modular flap door is less than the corresponding expected power, if yes, the energy storage part of the current modular flap door is charged until the corresponding expected power is reached to stop charging. The application utilizes the characteristics that the water temperature gradually decreases with the increase of water depth, and takes the heat dissipation of the energy storage part as the heat dissipation index of the energy storage part at different water depths. Since the charging and discharging of the energy storage part (such as a battery pack) will both release heat, the energy storage part at a colder water temperature has a larger temperature difference, thereby being more conducive to heat dissipation of the energy storage part. Therefore, the application allocates more charging power to the energy storage part at a colder water temperature, and more charging power means more power consumption. The whole heat dissipation process can be carried out in a colder water temperature environment, thereby ensuring good heat dissipation of the energy storage part throughout the process. In addition, the application introduces machine learning to predict future water temperature, so that the application can predict future water temperature changes and make charging preparations in advance, thereby eliminating the hysteresis of charging behavior. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 It is a structural schematic diagram of the modular flap door of the application; Figure 2 It is a structural schematic diagram of the open state of the modular flap door of the application; Figure 3 It is another schematic diagram of the open state of the modular flap door of the application; Figure 4 It is a step flow schematic diagram of one embodiment of the energy storage management method of the modular flap door of the application; Figure 5 It is a structural schematic diagram of one embodiment of the energy storage management device of the modular flap door of the application; Figure 6 It is a structural schematic diagram of one embodiment of the electronic equipment of the application; Figure 7 It is a structural schematic diagram of one embodiment of the storage medium of the application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort fall within the protection scope of the present application.

[0020] The terms "first", "second", "third" in the present application are only for descriptive purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", "third" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "plurality" is at least two, for example, two, three, etc., unless otherwise explicitly and specifically limited. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, movement condition, etc. between the components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0021] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification is not necessarily all referring to the same embodiment, or to the same alternative embodiment, nor is it necessary that all embodiments include the same feature, structure or characteristic. It will be explicitly understood by a person of ordinary skill in the art that the embodiments described herein can be combined with other embodiments.

[0022] As Figure 1 shown, the present embodiment provides an embodiment of the energy storage management method of the modular flap gate, in which the modular flap gate is applied to a layered water taking working gate, the layered water taking working gate includes at least one group of modular flap gates with different differentials, all the modular flap gates are clamped in the gate slot of the dam body and are used to rotate respectively according to different water taking requirements to achieve the purpose of being opened or closed respectively, each modular flap gate has a wireless power supply part and an energy storage part electrically connected with the wireless power supply part.

[0023] Preferably, referring to Figure 1 ,Figure 2 、 Figure 3 The tongue flap door is powered by wireless power supply to prevent excessive cables from affecting underwater environmental installation or operation and maintenance. In order to realize wireless power supply, the tongue flap door is designed in a modular manner. Each modular component carrying the tongue flap door includes a jack-up frame and a driving device installed on both sides of the jack-up frame and used to drive the rotation of the rotating shaft within the frame range of the jack-up frame. The tongue flap door is installed on the rotating shaft and is driven to rotate by the rotating shaft. A receiving coil for wireless power supply is installed in the jack-up frame. The transmitting coil for wireless power supply is installed in the gate slot. The gate slot is formed by pouring concrete during primary construction.

[0024] Specifically, as shown in Figure 4 The energy storage management method includes the following steps: Step S1, respectively acquiring the water surface based underwater depth of each modular tongue flap door, and respectively acquiring the water temperature of each underwater depth based on a preset detection interval.

[0025] Preferably, the water surface based underwater depth of different modular tongue flap doors can be directly measured, including physical measurement and infrared measurement, but attention should be paid to the refraction problem of light passing through the water surface, and it is recommended to calculate according to the engineering drawing and the overall water depth.

[0026] Step S2, training and learning the water temperature of all underwater depths by a machine learning machine to obtain a water temperature prediction model.

[0027] Preferably, any machine learning machine with prediction function can be used, such as linear regression, logistic regression, support vector machine, decision tree, random forest, etc.

[0028] Preferably, in order to ensure the prediction accuracy, the water temperature can use the data of the past one natural year.

[0029] Step S3, defining a preset prediction interval same as the preset detection interval step, and predicting a plurality of future water temperatures based on a plurality of preset prediction intervals by the water temperature prediction model.

[0030] Preferably, the preset detection interval and the preset prediction interval can be set to 10 minutes.

[0031] Step S4, acquiring the minimum temperature and the maximum temperature in all water temperatures and all future water temperatures.

[0032] For example, all water temperatures cover one natural year that has occurred, and all future water temperatures cover one natural day or one natural week in the future.

[0033] Step S5, taking the minimum temperature and the maximum temperature as the interval minimum value and the interval maximum value of the temperature interval respectively, and constructing the temperature interval.

[0034] Step S6, the temperature interval is equally divided into at least two consecutive sub-intervals.

[0035] Step S7, an expected power is assigned to each sub-interval, and all expected powers decrease with the increase of each sub-interval.

[0036] For example, the temperature interval of a water body with stratified water extraction from the water body temperature of the past year to the water body temperature of the next month is [5℃, 20℃], and if each 5℃ is divided into a sub-interval, then the sub-intervals are [5℃, 10℃), [10℃, 15℃), and [15℃, 20℃] in turn.

[0037] In order to prevent overcharging and over-discharging, the expected power should not be too close to 100%, and the expected power of each sub-interval can be set to 80%, 70%, and 60% in turn.

[0038] If a more detailed interval division is adopted, for example, each 1℃ is divided into a sub-interval, then the range of the expected power is preferably [50%, 80%].

[0039] Step S8, the future water body temperature of the underwater depth where each modular flap door is located is obtained respectively, and it is judged whether the remaining power of the current modular flap door is less than the corresponding expected power when the future water body temperature of the current modular flap door arrives, if yes, step S9 is executed.

[0040] Step S9, the energy storage part of the current modular flap door is charged until the corresponding expected power is reached and the charging is stopped.

[0041] Preferably, if not, it does not enter the charging process.

[0042] Further, step S9, the energy storage part of the current modular flap door is charged until the corresponding expected power is reached and the charging is stopped, and then the following steps are included: Step S10, the device temperature when the current energy storage part is not charged and the device temperature when the current energy storage part is charged are obtained based on a preset detection interval.

[0043] Preferably, the temperature measuring part can be installed before the modular flap door is shipped, and the temperature measuring function of the energy storage part can also be used, or it can be measured by itself.

[0044] Step S20, all the device temperatures when not charged are converted into a not-charged temperature curve based on the time process.

[0045] Step S30, the not-charged temperature curve is differentiated to obtain a not-charged temperature slope.

[0046] Step S40, all the device temperatures when charged are converted into a charged temperature curve based on the time process.

[0047] Step S50, the charging temperature curve is derived to obtain the charging temperature slope.

[0048] Step S60, when the uncharged temperature slope or the charging temperature slope exceeds the preset slope threshold, at least one of which exceeds the preset slope threshold, step S70 is executed.

[0049] Preferably, the uncharged temperature slope and the charging temperature slope are related to the density of the horizontal axis of the time course and the density of the vertical axis of the temperature value. In principle, the normal operating temperature rise is usually not more than 1-3°C per minute (specific to the model), the fast charging scene may temporarily reach 3-5°C per minute, at this time it must be matched with the heat dissipation design, in the extreme case (such as high load discharge) it may rise to 5-10°C per minute, but the continuous high temperature needs to be vigilant, and more than 10°C per minute may indicate internal short circuit or thermal runaway, which needs to be stopped immediately.

[0050] Therefore, if the unit density of the horizontal axis is 1 minute and the unit density of the vertical axis is 1°C, the temperature rise of 3°C per minute corresponds to two temperature slopes of 3, so the preset slope threshold can be set to 3.

[0051] Step S70, determine that the current energy storage device is abnormal.

[0052] Preferably, overcharging of the energy storage device can easily cause the voltage to rise rapidly with polarization, causing irreversible changes in the structure of the positive active material, decomposition of the electrolyte, generation of a large amount of gas, release of a large amount of heat, rapid rise of the battery temperature and internal pressure, melting or shrinking of the internal separator, causing the positive and negative materials to contact short circuit, and there is a risk of explosion and combustion, which affects the service life of the lithium battery; over-discharge can cause the internal pressure of the battery to rise, the reversibility of the positive and negative active materials to be destroyed, the electrolyte to decompose, the negative lithium to deposit, and the resistance to increase, thereby causing the battery temperature to rise rapidly, even if the charging can only partially recover, the capacity will also have a significant decay.

[0053] Further, step S70, determining that the current energy storage device is abnormal, further comprises the following steps: Step S100, marking the energy storage device with an uncharged temperature slope exceeding the preset slope threshold as a discharge abnormal energy storage device.

[0054] Step S200, marking all discharge abnormal energy storage devices corresponding to the modularized petal door as a discharge abnormal modularized petal door.

[0055] Step S300, respectively acquiring the position information and equipment number of each abnormal modularized petal door, and packaging them into a discharge abnormal data packet.

[0056] Step S400, send all discharge abnormal data packets to the external monitoring end.

[0057] Step S500, mark the energy storage device with a charging temperature slope exceeding the preset slope threshold as a charging abnormal energy storage device.

[0058] Step S600, repeat steps S200 to S300 with all charging abnormal energy storage devices as the execution subject to obtain charging abnormal data packets.

[0059] Step S700, send all charging abnormal data packets to the external monitoring end.

[0060] Further, step S1, respectively obtain the water-based underwater depth of each modular flap door, respectively obtain the water temperature of each underwater depth based on the preset detection interval, and then further include the following steps: Step S1000, respectively perform one-dimensional linear fitting on all water temperatures of each preset detection interval to obtain a water temperature function.

[0061] Step S2000, respectively determine whether each water temperature function is monotonically decreasing, and mark the water temperature function that is not monotonically decreasing as an abnormal function.

[0062] Step S3000, based on the time course, determine whether the previous and subsequent several water temperature functions of the current abnormal function are all abnormal functions, and if so, execute step S4000.

[0063] Step S4000, respectively obtain the inflection point of each abnormal function and the underwater depth corresponding to each inflection point.

[0064] Step S5000, mark the external temperature measuring element corresponding to the underwater depth with the highest occurrence frequency as a faulty temperature measuring element.

[0065] Step S6000, package all faulty temperature measuring elements and corresponding underwater depths into a fault data packet.

[0066] Step S7000, send the fault data packet to the external monitoring end.

[0067] Further, step S9, charge the energy storage device of the current modular flap door until the corresponding required amount of electricity is reached to stop charging, and then further include the following steps: Step S10000, record the charging start timestamp, charging duration, and energy storage device equipment number receiving charging based on each charging behavior, and package it into a charging record packet.

[0068] Step S20000, send the charging record packet to the external monitoring end.

[0069] Further, in step S2, the water temperature prediction model is obtained by training and learning the water temperature of all underwater depths by the machine learning machine, and specifically includes the following steps: In step S21, all water temperatures at the current underwater depth are integrated into a data set.

[0070] In step S22, the current data set is divided into a training set, a validation set, and a test set according to a preset ratio.

[0071] Preferably, the preset ratio is 70:15:15, that is, 70% training set, 15% validation set, and 15% test set.

[0072] In step S23, a neural network model with at least one hidden layer is defined.

[0073] Preferably, two hidden layers can be used, that is, the input layer, the first hidden layer, the second hidden layer, and the output layer are sequentially connected.

[0074] In step S24, the current training set is trained by the neural network model, and the weights and biases of the neural network model are updated by the back propagation algorithm according to the loss function of the training result and the current validation set.

[0075] In step S25, step S24 is repeatedly executed for several times until the loss function reaches a minimum value.

[0076] In step S26, the neural network model corresponding to the minimum value of the loss function is obtained and defined as the water temperature prediction model.

[0077] Preferably, a neural network usually needs to provide a large amount of data, that is, a data set, when training a model; the data set is generally divided into three categories, that is, the training set, the validation set, and the test set.

[0078] Wherein, an epoch is equal to a process of training once using all samples in the training set; the so-called training once refers to a forward pass and a back pass; when the number of samples in an epoch (that is, the training set) is too large, one training may consume too much time, and it is not necessary to use all data in the training set every time, so the entire training set needs to be divided into multiple small blocks, that is, multiple batches for training; an epoch is composed of one or more batches, and a batch is a part of the training set; the process of training a batch only uses a part of data, that is, a batch, and the process of training a batch is an iteration.

[0079] Preferably, the neural network training specifically comprises a perceptron, which is composed of two layers of neurons, an input layer receiving external input signals and passing them to an output layer, and the output layer is an M-P neuron, and the step function is f(x) = 1, x > 0, 0, x < 0, where the step function is a principle description and does not interact with other symbols.

[0080] Preferably, given a training data set, the weights (=1, 2,..., n) and the training bias can be obtained by learning, which can be understood as a fixed input of -1, 0, and the corresponding weight of a fixed value.

[0081] Preferably, the number of neural network training in the embodiment can be set to 10000 times.

[0082] Preferably, the learning rate of the first to 5000th epoch can be set to 0.01, the learning rate of the 5001th to 7500th epoch can be set to 0.001, and the learning rate of the 7501th to 10000th epoch can be set to 0.0001.

[0083] It can be understood that the neural network training of the embodiment mainly includes the following ideas: ①Initialize the weights and bias terms in the network.

[0084] Initialize the parameter values (output unit weights, bias terms and hidden unit weights, bias terms are all parameters of the model), which are used for forward propagation before activation to obtain the output value of each layer element, and then obtain the value of the loss function.

[0085] ②Activate the forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0086] ③According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0087] Calculate the error, calculate the gradient of the parameter with respect to the loss function or calculate the partial derivative according to the chain rule of calculus. For the partial derivative of a vector or matrix in a composite function, the partial derivative of the internal function of the composite function is always selected to be left multiplied; for the partial derivative of a scalar in a composite function, the partial derivative of the internal function of the composite function can be selected to be left multiplied or right multiplied.

[0088] ④Update the weights and bias terms in the neural network.

[0089] ⑤Repeat ②~④ until the loss function is less than the preset bias or the iteration number is used up, and output the parameters at this time as the current best parameters.

[0090] Further, step S3, defining a preset prediction interval same as the preset detection interval step, and predicting a plurality of future water temperatures based on a plurality of preset prediction intervals through the water temperature prediction model, comprising: Step S31, inputting the current test set into the water temperature prediction model corresponding to the current underwater depth.

[0091] Step S32, obtaining the future water temperature of the next preset prediction interval by forward propagation of the current water temperature prediction model.

[0092] Step S33, inputting the future water temperature of the next preset prediction interval into the current water temperature prediction model as the iteration subject, repeating step S32 to obtain a plurality of future water temperatures.

[0093] In this embodiment, the water surface-based underwater depth of each modular flap door is obtained, and the water temperature of each underwater depth is obtained based on the preset detection interval. The water temperature prediction model is obtained by training and learning the water temperature of all underwater depths through a machine learning machine. A preset prediction interval same as the preset detection interval step is defined, and a plurality of future water temperatures are predicted based on a plurality of preset prediction intervals through the water temperature prediction model. The minimum and maximum temperatures of all water temperatures and all future water temperatures are obtained. The minimum and maximum temperatures are respectively taken as the minimum and maximum values of the temperature interval, and the temperature interval is constructed. The temperature interval is equally divided into at least two continuous subintervals. Each subinterval is assigned an expected power, and all expected powers decrease with the increase of each subinterval. The future water temperature of each modular flap door is obtained, and it is judged whether the remaining power of the current modular flap door is less than the corresponding expected power when the future water temperature of the current modular flap door arrives. If so, charge the energy storage device of the current modular flap door until the corresponding expected power is reached. This embodiment takes advantage of the characteristic that water temperature gradually decreases with the increase of water depth, and uses the heat dissipation of the energy storage device as the heat dissipation index of the energy storage device at different water depths. Since the charging and discharging of the energy storage device (such as a battery pack) will generate heat, the energy storage device in colder water temperature has a larger temperature difference, which is more conducive to heat dissipation. Therefore, this embodiment allocates more charging capacity to the energy storage device in colder water temperature. More charging capacity means more power consumption, and the entire heat dissipation process can be carried out in a colder water temperature environment, thereby ensuring good heat dissipation of the energy storage device throughout the process. In addition, this embodiment introduces machine learning to predict future water temperature, so that it can predict future water temperature changes and prepare for charging in advance, thereby eliminating the hysteresis of charging behavior.

[0094] As Figure 2As shown, the embodiment provides a modular flap gate energy storage management device, which is applied to the energy storage management method in the above embodiment in the embodiment.

[0095] Specifically, the energy storage management device includes, in sequence, an underwater depth and temperature acquisition module 1, a water temperature prediction model acquisition module 2, a future water temperature prediction module 3, a future water temperature extreme value acquisition module 4, a temperature interval construction module 5, a temperature interval division module 6, an appropriate power assignment module 7, a modular flap gate residual power judgment module 8, and a modular flap gate energy storage component charging module 9.

[0096] The underwater depth and temperature acquisition module 1 is configured to acquire the water surface-based underwater depth of each modular flap gate and the water temperature of each underwater depth based on a preset detection interval, respectively. The water temperature prediction model acquisition module 2 is configured to train and learn the water temperature of all underwater depths by a machine learning machine to obtain a water temperature prediction model. The future water temperature prediction module 3 is configured to define a preset prediction interval identical to the preset detection interval step and predict a plurality of future water temperatures based on a plurality of preset prediction intervals by the water temperature prediction model. The future water temperature extreme value acquisition module 4 is configured to acquire the temperature minimum value and the temperature maximum value in all water temperatures and all future water temperatures. The temperature interval construction module 5 is configured to construct a temperature interval by taking the temperature minimum value and the temperature maximum value as the interval minimum value and the interval maximum value of the temperature interval, respectively. The temperature interval division module 6 is configured to divide the temperature interval into at least two continuous subintervals. The appropriate power assignment module 7 is configured to assign an appropriate power to each subinterval, and all appropriate powers decrease with the increase of each subinterval. The modular flap gate residual power judgment module 8 is configured to acquire the future water temperature of the underwater depth where each modular flap gate is located, and judge whether the residual power of the current modular flap gate is less than the corresponding appropriate power when the future water temperature of the current modular flap gate arrives. The modular flap gate energy storage component charging module 9 is configured to charge the energy storage component of the current modular flap gate if the residual power of the current modular flap gate is less than the corresponding appropriate power, and stop charging when the corresponding appropriate power is reached.

[0097] Further, the energy storage management device further includes, in sequence, an equipment temperature acquisition module, an uncharged temperature curve conversion module, an uncharged temperature slope acquisition module, a charged temperature curve conversion module, a charged temperature slope acquisition module, a charged temperature slope acquisition module, a slope judgment module, and an energy storage component abnormality determination module. The equipment temperature acquisition module is electrically connected to the modular flap gate energy storage component charging module 9.

[0098] The device temperature acquisition module is configured to acquire the device temperature of the energy storage device when not charging and the device temperature of the energy storage device when charging based on a preset detection interval; the not-charging temperature curve conversion module is configured to convert all the device temperatures when not charging into a not-charging temperature curve based on a time sequence; the not-charging temperature slope acquisition module is configured to derive the not-charging temperature curve to obtain a not-charging temperature slope; the charging temperature curve conversion module is configured to convert all the device temperatures when charging into a charging temperature curve based on a time sequence; the charging temperature slope acquisition module is configured to derive the charging temperature curve to obtain a charging temperature slope; the slope judgment module is configured to judge whether the not-charging temperature slope or the charging temperature slope exceeds a preset slope threshold; and the energy storage device abnormality judgment module is configured to judge that the current energy storage device is abnormal if at least one of the not-charging temperature slope and the charging temperature slope exceeds the preset slope threshold.

[0099] Further, the energy storage management device further comprises, in sequence, a discharge abnormal energy storage device marking module, a discharge abnormal modular flapper door marking module, a discharge abnormal data packet packaging module, a discharge abnormal data packet sending module, a charging abnormal energy storage device marking module, a charging abnormal data packet acquisition module, and a charging abnormal data packet sending module; the discharge abnormal energy storage device marking module is electrically connected to the energy storage device abnormality judgment module.

[0100] The discharge abnormal energy storage device marking module is configured to mark the energy storage device whose not-charging temperature slope exceeds the preset slope threshold as a discharge abnormal energy storage device; the discharge abnormal modular flapper door marking module is configured to mark the modular flapper door corresponding to all the discharge abnormal energy storage devices as a discharge abnormal modular flapper door; the discharge abnormal data packet packaging module is configured to acquire the position information and the device number of each abnormal modular flapper door respectively and package them into a discharge abnormal data packet; the discharge abnormal data packet sending module is configured to send all the discharge abnormal data packets to an external monitoring end; the charging abnormal energy storage device marking module is configured to mark the energy storage device whose charging temperature slope exceeds the preset slope threshold as a charging abnormal energy storage device; the charging abnormal data packet acquisition module is configured to repeatedly execute the discharge abnormal modular flapper door marking module to the discharge abnormal data packet packaging module with all the charging abnormal energy storage devices as the execution subject to obtain a charging abnormal data packet; and the charging abnormal data packet sending module is configured to send all the charging abnormal data packets to the external monitoring end.

[0101] Further, the energy storage management device further comprises, in sequence, a charging record packet acquisition module and a charging record packet sending module; the charging record packet acquisition module is electrically connected to the modular flapper door energy storage device charging module 9.

[0102] The charging record package acquisition module is configured to record a charging start timestamp, a charging duration, and a number of energy storage devices receiving charging each time a charging behavior occurs, and package the charging record into a charging record package.

[0103] Further, the underwater depth and temperature acquisition module 1 specifically comprises first, second, third, fourth, fifth, sixth, and seventh underwater depth and temperature acquisition units connected in sequence, and the seventh underwater depth and temperature acquisition unit is electrically connected with the water body temperature prediction model acquisition module 2.

[0104] The first underwater depth and temperature acquisition unit is configured to perform one-dimensional linear fitting on all water body temperatures of each preset detection interval, respectively, to obtain a water body temperature function; the second underwater depth and temperature acquisition unit is configured to determine whether each water body temperature function is monotonically decreasing, respectively, and mark the water body temperature function that is not monotonically decreasing as an abnormal function; the third underwater depth and temperature acquisition unit is configured to determine, based on a time sequence, whether the previous and subsequent several water body temperature functions of the current abnormal function are all abnormal functions; the fourth underwater depth and temperature acquisition unit is configured to obtain, if so, an inflection point of each abnormal function and a corresponding underwater depth of each inflection point, respectively; the fifth underwater depth and temperature acquisition unit is configured to mark the external temperature measuring element corresponding to the underwater depth with the highest occurrence frequency as a faulty temperature measuring element; the sixth underwater depth and temperature acquisition unit is configured to package all faulty temperature measuring elements and corresponding underwater depths into a fault data package; and the seventh underwater depth and temperature acquisition unit is configured to send the fault data package to an external monitoring end.

[0105] Further, the water body temperature prediction model acquisition module 2 specifically comprises first, second, third, fourth, fifth, and sixth water body temperature prediction model acquisition units connected in sequence, and the first water body temperature prediction model acquisition unit is electrically connected with the seventh underwater depth and temperature acquisition unit, and the sixth water body temperature prediction model acquisition unit is electrically connected with the future water body temperature prediction module 3.

[0106] The first water body temperature prediction model acquisition unit is configured to integrate all water body temperatures at the current underwater depth into one data set; the second water body temperature prediction model acquisition unit is configured to divide the current data set into a training set, a verification set and a test set according to a preset proportion; the third water body temperature prediction model acquisition unit is configured to define a neural network model with at least one hidden layer; the fourth water body temperature prediction model acquisition unit is configured to train the current training set through the neural network model, and update the weights and biases of the neural network model through a back propagation algorithm according to the training result and a loss function of the current verification set; the fifth water body temperature prediction model acquisition unit is configured to repeatedly execute the fourth water body temperature prediction model acquisition unit several times until the loss function reaches a minimum value; and the sixth water body temperature prediction model acquisition unit is configured to acquire the neural network model corresponding to the minimum value of the loss function and define the neural network model as a water body temperature prediction model.

[0107] Further, the future water body temperature prediction module 3 specifically includes a first future water body temperature prediction unit, a second future water body temperature prediction unit and a third future water body temperature prediction unit connected in sequence; the first future water body temperature prediction unit is electrically connected with the sixth water body temperature prediction model acquisition unit, and the third future water body temperature prediction unit is electrically connected with the future water body temperature extreme value acquisition module 4.

[0108] The first future water body temperature prediction unit is configured to input the current test set into the water body temperature prediction model corresponding to the current underwater depth; the second future water body temperature prediction unit is configured to obtain the future water body temperature of the next preset prediction interval through forward propagation of the current water body temperature prediction model; and the third future water body temperature prediction unit is configured to input the future water body temperature of the next preset prediction interval as an iteration subject into the current water body temperature prediction model, repeatedly execute the second future water body temperature prediction unit, and obtain several future water body temperatures.

[0109] It should be noted that the present embodiment is a functional module embodiment based on the above-mentioned method embodiment, and the preferred, expansion, limitation, example and principle explanation parts of the present embodiment can be seen from the above-mentioned embodiment, which will not be described herein again.

[0110] The embodiment obtains the water surface based underwater depth of each modular flap door, respectively, and obtains the water temperature of each underwater depth based on a preset detection interval; the water temperature of all underwater depths is trained and learned by a machine learning machine to obtain a water temperature prediction model; a preset prediction interval is defined which is the same as the preset detection interval step, and a plurality of future water temperatures are predicted based on a plurality of preset prediction intervals by the water temperature prediction model; the minimum and maximum temperatures in all water temperatures and all future water temperatures are obtained; the minimum and maximum temperatures are respectively taken as the interval minimum and interval maximum of a temperature interval to construct the temperature interval; the temperature interval is equally divided into at least two continuous subintervals; each subinterval is assigned an expected power, and all expected powers decrease with the increase of each subinterval; the future water temperature of the underwater depth where each modular flap door is located is obtained, and when the future water temperature of the current modular flap door arrives, it is judged whether the remaining power of the current modular flap door is less than the corresponding expected power, if so, the energy storage device of the current modular flap door is charged until the corresponding expected power is reached to stop charging. The embodiment takes advantage of the characteristic that water temperature gradually decreases with the increase of water depth, and uses the heat dissipation of the energy storage device as the heat dissipation index of the energy storage device at different water depths. Since the charging and discharging of the energy storage device (such as a battery pack) will generate heat, the energy storage device in colder water temperature has a larger temperature difference, which is more conducive to heat dissipation of the energy storage device. Therefore, the embodiment allocates more charging capacity to the energy storage device in colder water temperature, and more charging capacity means more power consumption. The entire heat dissipation process can be carried out in a colder water temperature environment, thereby ensuring good heat dissipation of the energy storage device throughout the process. In addition, the embodiment introduces machine learning to predict future water temperature, so that the embodiment can predict future water temperature changes and make charging preparations in advance, thereby eliminating the hysteresis of charging behavior.

[0111] Figure 6 is a structural schematic diagram of an electronic device of an embodiment of the present application. As shown in Figure 6 The electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0112] The memory 102 stores program instructions for implementing the energy storage management method of the modular flap door of any of the above embodiments.

[0113] The processor 101 is configured to execute the program instructions stored in the memory 102 to manage the energy storage of the modular flap door.

[0114] The processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 can be an integrated circuit chip having a processing capability of signals. The processor 101 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application-Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0115] Further, Figure 7 FIG. 1 is a structural schematic diagram of a storage medium according to an embodiment of the present application. Figure 7 The storage medium 11 according to the embodiment of the present application stores program instructions 111 capable of implementing all the methods described above, wherein the program instructions 111 can be stored in the storage medium in the form of a software product, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk or an optical disk, and various media capable of storing program codes, or a terminal device such as a computer, a server, a mobile phone, a tablet, etc.

[0116] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are merely schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0117] In addition, the various functional units in the embodiments of the present application can be integrated in one processing unit, or each can exist physically as a separate unit, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware, or in the form of a software functional unit. The above is only an implementation of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for energy storage management of a modular flap gate, wherein the modular flap gate is applied to a stratified water intake gate, the stratified water intake gate comprising at least one set of modular flap gates with different height differences, all modular flap gates being snapped into gate slots in the dam body and used to rotate according to different water intake needs to achieve their respective opening or closing purposes, each modular flap gate having a wireless power supply component and an energy storage component electrically connected to the wireless power supply component, characterized in that... The energy storage management method includes: Step S1: Obtain the underwater depth based on the water surface for each modular tongue valve, and obtain the water temperature at each underwater depth based on the preset detection interval. Step S2: Train and learn the water temperature at all underwater depths using a machine learning machine to obtain a water temperature prediction model; Step S3: Define a preset prediction interval with the same step size as the preset detection interval, and predict several future water temperatures based on several preset prediction intervals using the water temperature prediction model; Step S4: Obtain the minimum and maximum temperatures of all water bodies, as well as all future water body temperatures. Step S5: The minimum temperature and the maximum temperature are respectively used as the minimum and maximum values ​​of the temperature range to construct the temperature range; Step S6: Divide the temperature range into at least two consecutive sub-ranges; Step S7: Assign a required amount of electricity to each sub-interval, and the required amount of electricity decreases as each sub-interval increases; Step S8: Obtain the future water temperature at the underwater depth of each modular flap gate, and when the future water temperature of the current modular flap gate arrives, determine whether the remaining power of the current modular flap gate is less than the corresponding required power. If so, proceed to step S9. Step S9: Charge the energy storage component of the current modular tongue flap until it reaches the required power level, then stop charging.

2. The energy storage management method according to claim 1, characterized in that, Step S9: Charge the energy storage device of the current modular tongue flap until it reaches the required charge level, then stop charging. Afterwards, the process includes: Step S10: Based on the preset detection interval, obtain the device temperature of the current energy storage device when it is not charging and the device temperature when it is charging. Step S20: Convert all uncharged device temperatures into uncharged temperature profiles based on the time progression; Step S30: Differentiate the uncharged temperature curve to obtain the uncharged temperature slope; Step S40: Convert all device temperatures during charging into charging temperature curves based on the time progression; Step S50: Differentiate the charging temperature curve to obtain the charging temperature slope; Step S60: If it is determined whether the uncharged temperature slope or the charging temperature slope exceeds a preset slope threshold, then step S70 is executed if at least one of the uncharged temperature slope or the charging temperature slope exceeds the preset slope threshold. Step S70: Determine that the current energy storage device is malfunctioning.

3. The energy storage management method according to claim 2, characterized in that, Step S70: Determine that the current energy storage device is malfunctioning, then includes: Step S100: Mark the energy storage device whose uncharged temperature slope exceeds the preset slope threshold as an abnormal discharge energy storage device; Step S200: Mark all modular tongue valves corresponding to the abnormal discharge energy storage devices as abnormal discharge modular tongue valves; Step S300: Obtain the location information and device number of each abnormal modular tongue valve, and package them into a discharge abnormality data packet; Step S400: Send all abnormal discharge data packets to the external monitoring terminal; Step S500: Mark the energy storage device whose charging temperature slope exceeds the preset slope threshold as an abnormal charging energy storage device; Step S600: Repeat steps S200 to S300 with all abnormal charging energy storage devices as the execution subjects to obtain a charging abnormal data packet; Step S700: Send all charging error data packets to the external monitoring terminal.

4. The energy storage management method according to claim 1, characterized in that, Step S1: Obtain the underwater depth based on the water surface for each modular tongue valve, and obtain the water temperature at each underwater depth based on a preset detection interval. Then, the following steps are included: Step S1000: Perform univariate linear fitting on all water temperatures for each preset detection interval to obtain the water temperature function; Step S2000: Determine whether each water temperature function is monotonically decreasing, and mark the water temperature functions that are not monotonically decreasing as abnormal functions; Step S3000: Based on the time process, determine whether the preceding and following water temperature functions of the current abnormal function are all abnormal functions. If they are, then proceed to step S4000. Step S4000: Obtain the inflection point of each anomaly function and the corresponding underwater depth for each inflection point; Step S5000: Mark the external temperature measuring device corresponding to the underwater depth that appears most frequently as the faulty temperature measuring device; Step S6000: Package all faulty temperature sensors and their corresponding underwater depths into a fault data package; Step S7000: Send the fault data packet to the external monitoring terminal.

5. The energy storage management method according to claim 1, characterized in that, Step S9: Charge the energy storage device of the current modular tongue flap until it reaches the required charge level, then stop charging. Afterwards, the process includes: Step S10000: Record the charging start timestamp, charging duration, and energy storage device number receiving the charge for each charging behavior, and package them into a charging record package. Step S20000: Send the charging record package to the external monitoring terminal.

6. The energy storage management method according to claim 1, characterized in that, Step S2: Train and learn the water temperature at all underwater depths using a machine learning machine to obtain a water temperature prediction model, including: Step S21: Integrate the water temperatures of all bodies at the current underwater depth into a single dataset; Step S22: Divide the current dataset into a training set, a validation set, and a test set according to a preset ratio; Step S23: Define a neural network model with at least one hidden layer; Step S24: Train the current training set using the neural network model, and update the weights and biases of the neural network model using the backpropagation algorithm based on the training results and the loss function of the current validation set. Step S25: Repeat step S24 several times until the loss function reaches its minimum value; Step S26: Obtain the neural network model corresponding to the minimum value of the loss function and define it as the water temperature prediction model.

7. The energy storage management method according to claim 6, characterized in that, Step S3: Define a preset prediction interval with the same step size as the preset detection interval, and predict several future water temperatures based on several preset prediction intervals using the water temperature prediction model, including: Step S31: Input the current test set into the water temperature prediction model corresponding to the current underwater depth; Step S32: Obtain the future water temperature at the next preset prediction interval through forward propagation of the current water temperature prediction model; Step S33: Use the future water temperature at the next preset prediction interval as the input to the current water temperature prediction model, and repeat step S32 to obtain several future water temperatures.

8. A modular tongue-valve energy storage management device, wherein the energy storage management device is applied to the energy storage management method as described in any one of claims 1 to 7, characterized in that, The energy storage management device includes: The underwater depth and temperature acquisition module is used to acquire the underwater depth based on the water surface for each modular tongue valve, and to acquire the water temperature at each underwater depth based on a preset detection interval. The water temperature prediction model acquisition module is used to train and learn the water temperature at all underwater depths through a machine learning machine to obtain a water temperature prediction model. The future water temperature prediction module is used to define a preset prediction interval with the same step size as the preset detection interval, and to predict several future water temperatures based on several preset prediction intervals using the water temperature prediction model. The module for obtaining the maximum and minimum values ​​of future water body temperatures is used to obtain the temperatures of all water bodies, as well as the minimum and maximum temperatures among all future water body temperatures. A temperature range construction module is used to construct the temperature range by taking the minimum temperature value and the maximum temperature value as the minimum and maximum values ​​of the temperature range, respectively. A temperature range division module is used to divide the temperature range into at least two consecutive sub-ranges. The required power allocation module is used to allocate a required power based on each sub-interval, and all required power decreases as each sub-interval increases; The modular flap gate remaining power determination module is used to obtain the future water temperature at the underwater depth of each modular flap gate, and determine whether the remaining power of the current modular flap gate is less than the corresponding expected power when the future water temperature of the current modular flap gate arrives. The modular tongue-valve gate energy storage component charging module is used to charge the energy storage component of the current modular tongue-valve gate if the condition is met, until the corresponding required power is reached and then charging stops.

9. An electronic device, characterized in that, The method includes a processor and a memory coupled to the processor, the memory storing program instructions executable by the processor; when the processor executes the program instructions stored in the memory, it implements the energy storage management method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores program instructions, which, when executed by a processor, can implement the energy storage management method as described in any one of claims 1 to 7.

Images